Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.3494. Min Act: -0.1700
Data Index: 504129 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.2869. Min Act: -0.1700
Data Index: 2291220 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.2869. Min Act: -0.1700
Data Index: 3964169 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.2244. Min Act: -0.1700
Data Index: 4881915 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1932. Min Act: -0.1700
Data Index: 7968843 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.2244. Min Act: -0.1700
Data Index: 5783900 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1932. Min Act: -0.1700
Data Index: 1598198 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1932. Min Act: -0.1700
Data Index: 124043 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1619. Min Act: -0.1700
Data Index: 8013122 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1932. Min Act: -0.1700
Data Index: 7646725 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.0994. Min Act: -0.1700
Data Index: 2434817 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1306. Min Act: -0.1700
Data Index: 881477 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.1306. Min Act: -0.1700
Data Index: 7986727 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.0994. Min Act: -0.1700
Data Index: 7620528 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.0056. Min Act: -0.1700
Data Index: 70138 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3494. Min Range: -4.3494
Max Act: 3.9743. Min Act: -0.1700
Data Index: 3018520 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.0056. Min Act: -0.1700
Data Index: 4376032 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3494. Min Range: -4.3494
Max Act: 3.9743. Min Act: -0.1700
Data Index: 2060919 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3494. Min Range: -4.3494
Max Act: 4.0056. Min Act: -0.1700
Data Index: 3418983 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3494. Min Range: -4.3494
Max Act: 3.9743. Min Act: -0.1700
Data Index: 4062778 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19